github.com/instill-ai/component@v0.16.0-beta/pkg/connector/stabilityai/v0/README.mdx (about) 1 --- 2 title: "Stability AI" 3 lang: "en-US" 4 draft: false 5 description: "Learn about how to set up a VDP Stability AI connector https://github.com/instill-ai/instill-core" 6 --- 7 8 The Stability AI component is an AI connector that allows users to connect the AI models served on the Stability AI Platform. 9 It can carry out the following tasks: 10 11 - [Text To Image](#text-to-image) 12 - [Image To Image](#image-to-image) 13 14 ## Release Stage 15 16 `Alpha` 17 18 ## Configuration 19 20 The component configuration is defined and maintained [here](https://github.com/instill-ai/component/blob/main/pkg/connector/stabilityai/v0/config/definition.json). 21 22 ## Connection 23 24 | Field | Field ID | Type | Note | 25 | :--- | :--- | :--- | :--- | 26 | API Key (required) | `api_key` | string | Fill your Stability AI API key. To find your keys, visit - https://platform.stability.ai/account/keys | 27 28 ## Supported Tasks 29 30 ### Text To Image 31 32 Generate a new image from a text prompt. 33 34 | Input | ID | Type | Description | 35 | :--- | :--- | :--- | :--- | 36 | Task ID (required) | `task` | string | `TASK_TEXT_TO_IMAGE` | 37 | Engine (required) | `engine` | string | Stability AI Engine (model) to be used. | 38 | Prompts (required) | `prompts` | array[string] | An array of prompts to use for generation. | 39 | Weights | `weights` | array[number] | An array of weights to use for generation. | 40 | CFG Scale | `cfg_scale` | number | How strictly the diffusion process adheres to the prompt text (higher values keep your image closer to your prompt) | 41 | Clip Guidance Preset | `clip_guidance_preset` | string | Clip guidance preset | 42 | Height | `height` | integer | The image height | 43 | Width | `width` | integer | The image width | 44 | Sampler | `sampler` | string | Which sampler to use for the diffusion process. If this value is omitted we'll automatically select an appropriate sampler for you. | 45 | Samples | `samples` | integer | Number of images to generate | 46 | Seed | `seed` | integer | Random noise seed (omit this option or use `0` for a random seed) | 47 | Steps | `steps` | integer | Number of diffusion steps to run. | 48 | Style Preset | `style_preset` | string | Pass in a style preset to guide the image model towards a particular style. This list of style presets is subject to change. | 49 50 | Output | ID | Type | Description | 51 | :--- | :--- | :--- | :--- | 52 | Images | `images` | array[string] | Generated images | 53 | Seeds | `seeds` | array[number] | Seeds of generated images | 54 55 ### Image To Image 56 57 Modify an image based on a text prompt. 58 59 | Input | ID | Type | Description | 60 | :--- | :--- | :--- | :--- | 61 | Task ID (required) | `task` | string | `TASK_IMAGE_TO_IMAGE` | 62 | Engine (required) | `engine` | string | Stability AI Engine (model) to be used. | 63 | Prompts (required) | `prompts` | array[string] | An array of prompts to use for generation. | 64 | Init Image | `init_image` | string | Image used to initialize the diffusion process, in lieu of random noise. | 65 | Weights | `weights` | array[number] | An array of weights to use for generation. If unspecified, the model will automatically assign a default weight of 1.0 to each prompt. | 66 | Clip Guidance Preset | `clip_guidance_preset` | string | Clip guidance preset | 67 | Image Strength | `image_strength` | number | How much influence the `init_image` has on the diffusion process. Values close to `1` will yield images very similar to the `init_image` while values close to `0` will yield images wildly different than the `init_image`. The behavior of this is meant to mirror DreamStudio's "Image Strength" slider. <br/> <br/> This parameter is just an alternate way to set `step_schedule_start`, which is done via the calculation `1 - image_strength`. For example, passing in an Image Strength of 35% (`0.35`) would result in a `step_schedule_start` of `0.65`. | 68 | Cfg Scale | `cfg_scale` | number | How strictly the diffusion process adheres to the prompt text (higher values keep your image closer to your prompt) | 69 | Init Image Mode | `init_image_mode` | string | Whether to use `image_strength` or `step_schedule_*` to control how much influence the `init_image` has on the result. | 70 | Sampler | `sampler` | string | Which sampler to use for the diffusion process. If this value is omitted we'll automatically select an appropriate sampler for you. | 71 | Samples | `samples` | integer | Number of images to generate | 72 | Seed | `seed` | integer | Random noise seed (omit this option or use `0` for a random seed) | 73 | Step Schedule Start | `step_schedule_start` | number | Skips a proportion of the start of the diffusion steps, allowing the init_image to influence the final generated image. Lower values will result in more influence from the init_image, while higher values will result in more influence from the diffusion steps. (e.g. a value of `0` would simply return you the init_image, where a value of `1` would return you a completely different image.) | 74 | Step Schedule End | `step_schedule_end` | number | Skips a proportion of the end of the diffusion steps, allowing the init_image to influence the final generated image. Lower values will result in more influence from the init_image, while higher values will result in more influence from the diffusion steps. | 75 | Steps | `steps` | integer | Number of diffusion steps to run. | 76 | Style Preset | `style_preset` | string | Pass in a style preset to guide the image model towards a particular style. This list of style presets is subject to change. | 77 78 | Output | ID | Type | Description | 79 | :--- | :--- | :--- | :--- | 80 | Images | `images` | array[string] | Generated images | 81 | Seeds | `seeds` | array[number] | Seeds of generated images |